SLAM in the Dark: Self-Supervised Learning of Pose, Depth and Loop-Closure from Thermal Images

TL;DR

DarkSLAM is a deep learning-based thermal SLAM system that improves localization and mapping in low-light conditions by integrating attention mechanisms and thermal-specific features, outperforming existing methods in outdoor nighttime environments.

Contribution

The paper introduces DarkSLAM, a novel thermal SLAM system that leverages attention mechanisms for enhanced pose and depth estimation in challenging thermal environments.

Findings

DarkSLAM outperforms existing thermal SLAM methods in outdoor experiments.

The system achieves high-precision localization in nighttime and low-light conditions.

Thermal depth-based loop closure improves robustness in low-texture scenes.

Abstract

Visual SLAM is essential for mobile robots, drone navigation, and VR/AR, but traditional RGB camera systems struggle in low-light conditions, driving interest in thermal SLAM, which excels in such environments. However, thermal imaging faces challenges like low contrast, high noise, and limited large-scale annotated datasets, restricting the use of deep learning in outdoor scenarios. We present DarkSLAM, a noval deep learning-based monocular thermal SLAM system designed for large-scale localization and reconstruction in complex lighting conditions.Our approach incorporates the Efficient Channel Attention (ECA) mechanism in visual odometry and the Selective Kernel Attention (SKA) mechanism in depth estimation to enhance pose accuracy and mitigate thermal depth degradation. Additionally, the system includes thermal depth-based loop closure detection and pose optimization, ensuring robust performance in low-texture thermal scenes. Extensive outdoor experiments demonstrate that DarkSLAM significantly outperforms existing methods like SC-Sfm-Learner and Shin et al., delivering precise localization and 3D dense mapping even in challenging nighttime environments.